Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/chancy24/codex-knowledge-base-skill/project-knowledge-maintainernpx skills add chancy24/codex-knowledge-base-skill --skill project-knowledge-maintainergit clone --depth 1 https://github.com/chancy24/codex-knowledge-base-skillWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00033 | $0.01136 |
| Opus 5 | $0.00016 | $0.00568 |
| Sonnet 5 | $0.00007 | $0.00227 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
project-knowledge-maintainer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Knowledge Maintainer
Purpose
Use this Skill to initialize, maintain, and evolve a project-level knowledge base for AI coding agents. The knowledge base helps future agent sessions understand project purpose, architecture, interfaces, decisions, bugs, and recent changes without rediscovering everything from scratch.
Keep the workflow tool-neutral. It should be usable by Codex, Claude Code, Cursor, Gemini CLI, and other coding agents that can read project files and follow repository-local instructions.
When To Use
Use this Skill when the user asks to:
- initialize a project knowledge base
- summarize or document a project
- fix a bug and preserve the repair experience
- add or change a feature
- add or change an API, schema, command, or data format
- record a technical decision or tradeoff
- organize raw project materials into structured knowledge
- review or retrospect a completed development session
- update
AGENTS.mdor files underknowledge/
Inputs
Common inputs include:
- The current repository or target project path.
- Existing project files, source code, docs, issues, logs, or raw materials.
- The user's current task and any implementation changes made during the session.
- Existing
AGENTS.md,knowledge/,raw/, orskills/content if present.
Outputs
Expected outputs include:
AGENTS.mdproject rules.knowledge/overview.mdproject overview.knowledge/business.mdbusiness logic and usage scenarios.knowledge/architecture.mdsystem architecture and data flow.knowledge/api.mdinterfaces, schemas, commands, and data structures.knowledge/decisions.mdtechnical decisions and tradeoffs.knowledge/bugs.mdbug history, root causes, fixes, and prevention rules.knowledge/changelog.mdsession-level change records.- Optional
raw/and project-localskills/folders. - A short final report listing what was updated and what still needs verification.
Workflow
- Read project rules first:
AGENTS.mdif present.knowledge/overview.mdknowledge/architecture.mdknowledge/decisions.mdknowledge/bugs.md
- If initializing a repository, use the templates in
references/templates/or run the initializer script from this package. - Understand the current task and identify what changed:
- project goal or business logic
- architecture or module boundaries
- API, command, data file, schema, or return structure
- bug symptom, root cause, fix, or prevention rule
- technical decision or tradeoff
- user-facing behavior or UI convention
- Update only the relevant knowledge files.
- Remove or reconcile duplicate, stale, or contradictory content.
- Always update
knowledge/changelog.mdafter important work. - Report the updated files and any missing validation.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 265 B
- references/playbook.md 2.1 KB
- references/templates/AGENTS.template.md 1.7 KB
- references/templates/knowledge/api.md 1.5 KB
- references/templates/knowledge/architecture.md 1.2 KB
- references/templates/knowledge/bugs.md 1.6 KB
- references/templates/knowledge/business.md 1.1 KB
- references/templates/knowledge/changelog.md 1.3 KB
- references/templates/knowledge/decisions.md 1.4 KB
- references/templates/knowledge/overview.md 1.2 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 143 lines · 33 tokens per session scan A f5bc37e1cb42
project-knowledge-maintainer is a skill published in the GitHub repository chancy24/codex-knowledge-base-skill (1 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 1,136 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
nopua
The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior, or user frustration ('try harder', 'figure it out', '换个方法', '为什么还不行').…
weave
Parallel strand orchestration — decompose a task into 3+ independently scoped strands, fan out real subagents (worktree-isolated when they write files), and coordinate through a session file and Insight Capsules. Use ONLY when the user explicitly invokes it by name or slash command.
mcp-media-inbox-triage
Find media, partnership, and high-intent requests buried in a shared Gmail inbox, summarize the useful ones, and route them to the right owner through Zapier MCP.
customer-deck-builder
Build tailored customer-facing sales or customer success decks from approved account context and generate the presentation with Gamma through Zapier MCP.
premortem
First-principles premortem on a high-stakes plan: assume failure 6–18 months out, reconstruct causal death chains, surface hidden assumptions, deliver a revised reversibility-weighted plan. Use ONLY when the user explicitly invokes it by name or slash command.